Unsupervised Health Indicator Construction by a Novel Degradation-Trend-Constrained Variational Autoencoder and Its Applications

Health indicator (HI) affects the accuracy and reliability of the remaining useful life (RUL) prediction model. The hidden variables of variational autoencoder (VAE) can represent the HI values for a life-cycle dataset with obvious degradation trend. However, for an irregular dataset of a rotary machine, it is still a great challenge to construct the HI that can effectively represent the machinery degradation tendency. Therefore, this work proposes a novel degradation-trend-constrained VAE (DTC-VAE) to construct the HI vector with the distinct degradation trend. Firstly, the multi-dimensional time-domain and frequency-domain characteristics are calculated via the collected vibration samples. Secondly, a new degradation-constraint loss term is proposed and introduced into VAE for constructing DTC-VAE. Thirdly, with the multi-dimensional features and DTC-VAE, various HIs can be generated without supervision. The proposed method is applied to construct the HI vectors of bearing life-cycle datasets and gear fatigue datasets, and then macroscopic-microscopic-attention-based LSTM (MMALSTM) is used to predict the corresponding RULs with the constructed HIs. Via several contrast experiments, the results prove that the proposed unsupervised HI construction approach is superior to other typical methods, and the obtained HI vectors are more suitable for the RUL prediction.